]> 2026-04-04T17:31:30+02:00 Publications:Offline Handwritten Amharic Word Recognition Using HMMs 500 en <p>This paper describes two appraches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by DEHR dataset of unconstrained handwritten documents collected from various sources.</p> http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:728445 92 Proceedings SSBA '09 : Symposium on Image Analysis, Halmstad University, Halmstad, March 18-20, 2009 Book Chapter 89 Offline Handwritten Amharic Word Recognition Using HMMs 2009 2016-09-30T20:38:58Z 2457662.3603935 Offline Handwritten Amharic Word Recognition Using HMMs 500 0 plainlist list 1 [[:Publications:Offline Handwritten Amharic Word Recognition Using HMMs]] Offline Handwritten Amharic Word Recognition Using HMMs# QUERYd5a69626295c2ae650e91f23c4c3e9eb 500 [2,"smw-datavalue-property-restricted-annotation-use","Publisher"] Offline Handwritten Amharic Word Recognition Using HMMs# ERR6c155b5d70b69ddb590b4f2e73389c2a 500 [2,"smw-datavalue-property-restricted-annotation-use","Author"] Offline Handwritten Amharic Word Recognition Using HMMs# ERRe24f17e090c98448f3de99d03182b7b6